Don't make LLMs honest. Make every factual claim auditable. — An LLM Claim Auditing Layer with T1-T7 truth gradients. 98.1% business effectiveness on LiarBench v0.2.

Clean up Claude's token vomit with a separate LLM. Save your tokens, Opus is hopeless

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Universal AI behavior rule framework — pin your 5-10 rules so AI doesn't drift in long tasks. Dev-scenario preset built in; switch to any scenario in one line. Claude / Codex / Cursor / Hermes. Zero LLM, zero network, zero deps.

Automated TDD enforcement for Claude Code

Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deterministic spec passes, and there is no "done" without live acceptance evidence. Spec-first, verification-gated, forbidden-paths enforced.

One command to cut token usage by up to 50%+

A Socratic supervision layer for AI coding agents.

Real-time behavioral enforcement for Claude Code. Monitors AI actions, detects violations, and interrupts misbehavior. Also has a cute pet.

Prompt injection scanner for AI coding tools (Claude Code / Codex / etc). Runs DeBERTa/Llama transformers via Candle or ONNX in Rust

The first AI plugin that speaks first. Code-enforced learning + active forgetting + PAC (Proactive Accountability Challenge). Works with Claude Code, Gemini CLI, Hermes, OpenClaw.